註冊並分享邀請連結,可獲得影片播放與邀請獎勵。

Sauers
@Sauers_
gnome
加入 March 2024
2K 正在關注    22.8K 粉絲
Training the model to detect when it is in training vs. deployment works too! The model can even generalize from vLLM deployment training to SGLang deployment. We do this by recording activations from layer 34 in Hugging Face Trainer's training step and in vLLM's compiled serving. Then, we swap in the attention and residual stream from the Hugging Face copy and SFT the model to predict "Yes," and to predict "No" when we swap in from vLLM instead. The model learns how its training vs. deployment environment affects its first 34 layers.
顯示更多
0
1
161
1
轉發到社區